# What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time

arXiv: https://arxiv.org/abs/2603.19880 · HTML: https://mlsanity.com/paper/2603.19880/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 30 of 33)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Process Reinforcement through Implicit Rewards](https://mlsanity.com/paper/2502.01456/) (2025)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Absolute Zero: Reinforced Self-play Reasoning with Zero Data](https://mlsanity.com/paper/2505.03335/) (2025)
- [Reinforcement Learning for Reasoning in Large Language Models with One Training Example](https://mlsanity.com/paper/2504.20571/) (2025)
- [Learning to Reason without External Rewards](https://mlsanity.com/paper/2505.19590/) (2025)
- [The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning](https://mlsanity.com/paper/2506.01347/) (2025)
- [Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization](https://mlsanity.com/paper/2504.05812/) (2025)
- [RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold](https://mlsanity.com/paper/2406.14532/) (2024)
- [On Designing Effective RL Reward at Training Time for LLM Reasoning](https://mlsanity.com/paper/2410.15115/) (2024)
- [Can Large Reasoning Models Self-Train?](https://mlsanity.com/paper/2505.21444/) (2025)
- [Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.08745/) (2025)
- [Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation](https://mlsanity.com/paper/2509.15194/) (2025)
- [ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism](https://mlsanity.com/paper/2508.11356/) (2025)
- [SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models](https://mlsanity.com/paper/2509.23863/) (2025)
- [Heimdall: test-time scaling on the generative verification](https://mlsanity.com/paper/2504.10337/) (2025)
- [Mirror-Consistency: Harnessing Inconsistency in Majority Voting](https://mlsanity.com/paper/2410.10857/) (2024)
- [Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting](https://mlsanity.com/paper/2510.08696/) (2025)
- [SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization](https://mlsanity.com/paper/2511.17938/) (2025)
- [Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking](https://mlsanity.com/paper/2509.25787/) (2025)
- [Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning](https://mlsanity.com/paper/2511.01191/) (2025)
- [Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models](https://mlsanity.com/paper/2204.00471/) (2022)

## Built on by (most cited first, 12 of 12)

- [Consensus as Privileged Context for Label-Free Self-Distillation](https://mlsanity.com/paper/2607.13643/) (2026)
- [Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation](https://mlsanity.com/paper/2604.06950/) (2026)
- [AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?](https://mlsanity.com/paper/2608.00155/) (2026)
- [TTPO: Test-Time Policy Optimization](https://mlsanity.com/paper/2608.27448/) (2026)
- [Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-Conditioned Verification](https://mlsanity.com/paper/2606.03608/) (2026)
- [Hi-TTRL: Regulating Consensus with Hints for Test-Time Reinforcement Learning](https://mlsanity.com/paper/2608.03545/) (2026)
- [USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning](https://mlsanity.com/paper/2607.03900/) (2026)
- [Unsupervised Post-Training of Foundation Models: A Survey](https://mlsanity.com/paper/2608.24982/) (2026)
- [Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning](https://mlsanity.com/paper/2609.17386/) (2026)
- [Learning via Self-Consistency for Diffusion-based Video Reasoning](https://mlsanity.com/paper/2609.36826/) (2026)
- [Sharpen Before You Adapt: Data-Free Entry-State Sharpening for Test-Time Reinforcement Learning](https://mlsanity.com/paper/2610.00903/) (2026)
- [SelectTTRL: Representation-Guided Data Selection for Efficient Test-Time Reinforcement Learning](https://mlsanity.com/paper/2610.16104/) (2026)

## Abstract (arXiv)

Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving pseudo-rewards from majority voting consensus. However, existing TTRL methods rely exclusively on positive pseudo-labeling strategies. Such reliance becomes vulnerable under challenging scenarios where answer distributions are highly dispersed, resulting in weak consensus that inadvertently reinforces incorrect trajectories as supervision signals. In this paper, we propose SCRL (Selective-Complementary Reinforcement Learning), a robust test-time reinforcement learning framework that effectively mitigates label noise amplification. SCRL develops Selective Positive Pseudo-Labeling, which enforces strict consensus criteria to filter unreliable majorities. Complementarily, SCRL introduces Entropy-Gated Negative Pseudo-Labeling, the first negative supervision mechanism in TTRL, to reliably prune incorrect trajectories based on generation uncertainty. Extensive experiments on multiple reasoning benchmarks demonstrate that SCRL achieves substantial improvements over baselines, while maintaining robust generalization and training stability under constrained rollout budgets. Our code is available at https://github.com/Jasper-Yan/SCRL.